I have a pandas dataframe of 10 columns and trying to get bar plot using Bokeh.
The HTML file has the complete plot when I use plot_width=10000.
However when I increase the plot width(so that there is space between x axes values) to 30000, the plot does not fill beyond 2010. Here is the complete code. Please suggest the way forward.
from bokeh.palettes import Viridis6 as palette
from bokeh.transform import factor_cmap
from bokeh.models import ColumnDataSource,FactorRange,HoverTool
from bokeh.palettes import Spectral6
from flask import Flask, request, render_template, session, redirect,send_file
import numpy as np
import pandas as pd
from bokeh.plotting import figure, show, output_file,save
from bokeh.embed import components,file_html
from bokeh.resources import CDN
from bokeh.layouts import row,column
from bokeh.core.properties import value
dates = pd.date_range('20050101', periods=3900)
df = pd.DataFrame(np.random.randn(3900, 10), index=dates, columns=list('ABCDEFGHIJ'))
s = df.resample('M').mean().stack()
s.index = [s.index.get_level_values(0).strftime('%Y-%m-%d'),s.index.get_level_values(1)]
x = s.index.values
l1=list(s.index.levels[1])
counts = s.values
source = ColumnDataSource(data=dict(x=x, counts=counts))
p = figure(x_range=FactorRange(*x), plot_height=250,plot_width=30000, title='Plotting data',
toolbar_location=None, tools="")
p.vbar(x='x', top='counts', width=1, source=source, line_color="white")
p.y_range.start = s.values.min()
p.y_range.end = s.values.max()
p.x_range.range_padding = 0.01
p.y_range.range_padding = 0.01
p.xaxis.major_label_orientation = 1
p.xgrid.grid_line_color = None
output_file('test_plot.html')
save([p])
show(p)
This works fine for me with Bokeh 1.0.4 and OSX/Safari. I suspect this is a limitation/issue with the underlying HTML Canvas implementation in whatever browser you are using, in which case there is nothing we can do about it. The only suggestions I can make are to split the plot up into smaller subplots, or use a different browser (or possibly different version of the same browser)
Related
I want to add labels with the values above the bars like here: How to add data labels to a bar chart in Bokeh? but don't know how to do it. My code looks different then other examples, the code is working but maybe it is not the right way.
My code:
from bokeh.io import export_png
from bokeh.io import output_file, show
from bokeh.palettes import Spectral5
from bokeh.plotting import figure
from bokeh.sampledata.autompg import autompg_clean as df
from bokeh.transform import factor_cmap
from bokeh.models import ColumnDataSource, ranges, LabelSet, Label
import pandas as pd
d = {'lvl': ["lvl1", "lvl2", "lvl2", "lvl3"],
'feature': ["test1", "test2","test3","test4"],
'count': ["5", "20","8", "90"]}
dfn = pd.DataFrame(data=d)
sourceframe = ColumnDataSource(data=dfn)
groupn = dfn.groupby(by=['lvl', 'feature'])
index_cmapn = factor_cmap('lvl_feature', palette=Spectral5, factors=sorted(dfn.lvl.unique()), end=1)
pn = figure(plot_width=800, plot_height=300, title="Count",x_range=groupn, toolbar_location=None)
labels = LabelSet(x='feature', y='count', text='count', level='glyph',x_offset=0, y_offset=5, source=sourceframe, render_mode='canvas',)
pn.vbar(x='lvl_feature', top="count_top" ,width=1, source=groupn,line_color="white", fill_color=index_cmapn, )
pn.y_range.start = 0
pn.x_range.range_padding = 0.05
pn.xgrid.grid_line_color = None
pn.xaxis.axis_label = "levels"
pn.xaxis.major_label_orientation = 1.2
pn.outline_line_color = None
pn.add_layout(labels)
export_png(pn, filename="color.png")
I think it has something to do with my dfn.groupby(by=['lvl', 'feature']) and the (probably wrong) sourceframe = ColumnDataSource(data=dfn).
The plot at this moment:
You can add the groups names in the initial dictionary like this:
d = {'lvl': ["lvl1", "lvl2", "lvl2", "lvl3"],
'feature': ["test1", "test2","test3","test4"],
'count': ["5", "20","8", "90"],
'groups': [('lvl1', 'test1'), ('lvl2', 'test2'), ('lvl2', 'test3'), ('lvl3', 'test4')]}
And then call LabelSet using as x values the groups.
labels = LabelSet(x='groups', y='count', text='count', level='glyph',x_offset=20, y_offset=0, source=sourceframe, render_mode='canvas',)
In this way the labels appear. Note that I played a bit with the offset to check if that was the problem, you can fix that manually.
I am trying to represent the data using the bokeh scatter.
Here is my code:
from bokeh.plotting import Scatter, output_file, show import pandas
df=pandas.Dataframe(colume["X","Y"])
df["X"]=[1,2,3,4,5,6,7]
df["Y"]=[23,43,32,12,34,54,33]
p=Scatter(df,x="X",y="Y", title="Day Temperature measurement", xlabel="Tempetature", ylabel="Day")
output_file("File.html")
show(p)
The Output should look like this:
Expected Output
The error is:
ImportError Traceback (most recent call
> last) <ipython-input-14-1730ac6ad003> in <module>
> ----> 1 from bokeh.plotting import Scatter, output_file, show
> 2 import pandas
> 3
> 4 df=pandas.Dataframe(colume["X","Y"])
> 5
ImportError: cannot import name 'Scatter' from 'bokeh.plotting'
(C:\Users\LENOVO\Anaconda3\lib\site-packages\bokeh\plotting__init__.py)
I had also found that the Scatter is no longer maintained now. Is there is any way to use it?
Also which alternative do I have to represent the data same as the Scatter using any another python libraries?
Using older version of Bokeh will resolve this issue?
Scatter (with a capital S) has never been part of bokeh.plotting. It used to be a part of the old bokeh.charts API that was removed several years ago. However, it is not needed at all to create basic scatter plots, since all the glyph methods in bokeh.plotting (e.g circle, square) are all implicitly scatter-type functions to begin with:
from bokeh.plotting import figure, show
import pandas as pd
df = pd.DataFrame({"X" :[1,2,3,4,5,6,7],
"Y": [23,43,32,12,34,54,33]})
p = figure(x_axis_label="Tempetature", y_axis_label="Day",
title="Day Temperature measurement")
p.circle("X", "Y", size=15, source=df)
show(p)
Which yields:
You can also just pass the data directly to circle as in the other answer.
If you want to do fancier things, like map the marker type based on a column there is also a plot.scatter (lower case s) methods on the figure:
from bokeh.plotting import figure, show
from bokeh.sampledata.iris import flowers
from bokeh.transform import factor_cmap, factor_mark
SPECIES = ['setosa', 'versicolor', 'virginica']
MARKERS = ['hex', 'circle_x', 'triangle']
p = figure(title = "Iris Morphology")
p.xaxis.axis_label = 'Petal Length'
p.yaxis.axis_label = 'Sepal Width'
p.scatter("petal_length", "sepal_width", source=flowers, legend_field="species", fill_alpha=0.4, size=12,
marker=factor_mark('species', MARKERS, SPECIES),
color=factor_cmap('species', 'Category10_3', SPECIES))
show(p)
which yields:
If you look up "scatter" in the docs, you'll find
Scatter Markers
To scatter circle markers on a plot, use the circle() method of Figure:
from bokeh.plotting import figure, output_file, show
# output to static HTML file
output_file("line.html")
p = figure(plot_width=400, plot_height=400)
# add a circle renderer with a size, color, and alpha
p.circle([1, 2, 3, 4, 5], [6, 7, 2, 4, 5], size=20, color="navy", alpha=0.5)
# show the results
show(p)
To work with dataframes, just pass in the columns like df.X and df.Y to the x and y args.
from bokeh.plotting import figure, show, output_file
import pandas as pd
df = pd.DataFrame(columns=["X","Y"])
df["X"] = [1,2,3,4,5,6,7]
df["Y"] = [23,43,32,12,34,54,33]
p = figure()
p.scatter(df.X, df.Y, marker="circle")
#from bokeh.io import output_notebook
#output_notebook()
show(p) # or output to a file...
I want to draw a circle with bokeh, the color of this circle depends on a column of DataFrame. But I got an empty plot. If i don't specify a color argument for p.circle, it'll work fine.
Here is the code, you can copy and paste and run it.
from bokeh.plotting import figure, output_file, show
from bokeh.models import ColumnDataSource, CategoricalColorMapper
from bokeh.palettes import Spectral11
import pandas as pd
df = pd.DataFrame({
'price':[10,15,20,25,30],
'action':[0,1,0,2,3],
'sign':[0,-1,0,1,-1]
})
source = ColumnDataSource(data=dict(
index=df.index,
price=df.price,
action=df.action,
sign=df.sign
))
color_mapper = CategoricalColorMapper(factors= [str(i) for i in list(df.sign.unique())], palette=Spectral11)
p = figure(plot_width=800, plot_height=400)
# this works fine
p.circle('index', 'price', radius=0.2 , source=source)
# this don't work
p.circle('index', 'price', radius=0.2 , color={'field':'sign', 'transform':color_mapper}, source=source)
show(p)
Bokeh doesn't like it when you take some information from a ColumnDataSource, and other information from a different source. This worked for me(in a notebook):
from bokeh.plotting import figure, output_notebook, show
from bokeh.models import ColumnDataSource, CategoricalColorMapper
from bokeh.palettes import Spectral11
import pandas as pd
output_notebook()
df = pd.DataFrame({
'price':[10,15,20,25,30],
'action':[0,1,0,2,3],
'sign':[0,-1,0,1,-1],
})
source = ColumnDataSource(data=dict(
index=df.index,
price=df.price,
action=df.action,
sign=df.sign,
color=[Spectral11[i+1] for i in df.sign]
))
p = figure(plot_width=800, plot_height=400)
# this don't work
p.circle('index', 'price', radius=0.2 ,
color='color',
source=source)
show(p)
I am trying to append an AdjointLayout of a Scatter plot with two supporting histograms to a Bokeh dashboard. However, whenever trying to incorporate the two in a single row, the Bokeh widgets encounter display issues and the AdjointLayout never scales. Is this the current expected behavior or is here a different approach I need to take to currently accomplish this?
Minimal Example of the problem:
import numpy as np
import pandas as pd
import holoviews as hv
from bokeh.layouts import layout
from bokeh.models import Select
from bokeh.io import curdoc
renderer = hv.renderer('bokeh').instance(mode='server')
np.random.seed(10)
data = np.random.rand(100,4)
opts = {}
opts['color_index'] = 2
opts['size_index'] = 3
opts['scaling_factor'] = 50
points = hv.Points(data, vdims=['z', 'size']).opts(plot=opts)
fields = ['berry', 'cherry', 'dairy']
x = Select(title='X-Axis:', value=fields[0], options=fields)
y = Select(title='Y-Axis:', value=fields[1], options=fields)
dashboard = points + points[0.3:0.7, 0.3:0.7].hist()
app = renderer.get_plot(dashboard).state
dashboard = layout([
[[x, y], app],
])
curdoc().add_root(dashboard)
Using Bokeh 0.13.0 and Holoviews 1.10.5
I am running the following code to render a plot with dates in the x axis and floats in the y axis:
import pandas as pd
from bokeh.plotting import figure, output_file, show
from bokeh.models import DatetimeTickFormatter
from bokeh.charts import Bar, Line, show
def datetime(x):
return pd.DataFrame(x, dtype='datetime64')
openxbids = pd.read_csv('data')
openxbids.sort_values('date')
output_file("lines.html")
p = figure(width=800, height=250, x_axis_type="datetime")
p.line(datetime(openxbids['date']), openxbids['bids'], color = 'navy', alpha=0.5)
show(p)
However, when I run this, I get a graph without any data plotted. The x and y axis ranges seem to be correctly detected. What am I missing?